Colin Xiang

Results 10 comments of Colin Xiang

I also meet the same problem, I think there are two way to solve it: (1) Modify the config file: "dtu_wde3.yaml", the parameter "NUM_WORKERS" from 64 to 8, then it...

> @lt-xiang @DingYikang > > > Hi,tnt上的点云融合我们默认使用的是'dynamic'而不是'normal',建议您不修改默认脚 > > 为什么我融合出来的点云文件只有911kB > > ![image](https://user-images.githubusercontent.com/75787742/196411199-9446711f-aa74-4176-9484-b3dfaa9071d9.png) > > 什么都没有 我的问题已经排查到了。需要用作者的pre-processed 的TAT数据。原始的TAT数据里面camera.txt文件深度范围格式不一样

> @lt-xiang 你好,感谢解答,你是说测试的是intermediate下的嘛?有个short-range-cameras-for-mvsnet这个嘛?我测试的advance的几个场景 是的,测试了Family数据集。我下载是处理后的数据集。short-range-cameras-for-mvsnet这个是原始数据集里面的

> ![image](https://user-images.githubusercontent.com/89020229/179352137-e3cc7aee-2b0c-440e-b21d-a8110f71efe0.png) I have read your paper,got the information that you refined the 3D representation from neus.So could I just get the center,radius and bbox_max and min from "gen_cameras.py" in...

> Hi, Have you solved this issue ? I have the same situation when image_downscale is set to 8

你好,请问你解决了这个问题了吗

还没有,它这个代码小问题挺多的 canguanxuexi ***@***.***>于2023年9月16日 周六09:00写道: > 你好,请问你解决了这个问题了吗 > > 你好,请问你解决了吗 > > — > Reply to this email directly, view it on GitHub > , > or unsubscribe > > ....

> I used your provided code "eval_rcmvsnet_tanks.py" and with its own threshold parameters as you see below: > > scans = ['Family', 'Francis', 'Horse', 'Lighthouse', 'M60', 'Panther', 'Playground', 'Train'] >...